Adaptive Reasoning

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would...

Security Scan

The skill's purpose and footprint are plausible, but its instructions contain implementation mismatches and autonomy directives that could change agent behavior without clear platform support or user consent.

Purpose & Capability

The skill claims to assess task complexity and toggle a 'reasoning' mode; it requests no credentials, binaries, or installs, which is proportionate. However the SKILL.md says it "triggers on every user message" while the registry flags do not set always:true — a mismatch between stated runtime trigger behavior and declared privileges.

Instruction Scope

The instructions tell the agent to automatically enable/disable reasoning via a 'session_status' tool or '/reasoning on' command and to "Do not ask. Just activate." The skill does not declare use of any specific platform tool, so it's unclear whether those commands exist or whether the skill has permission to call them. The instructions also mandate appending icons to every response, which modifies output format broadly. These directives grant the skill broad control over session-level behavior and agent outputs without declaring where/how that control is available.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk.

Credentials

No environment variables, credentials, or config paths are requested; declared requirements are minimal and proportionate to the stated purpose.

Persistence & Privilege

always is false (good). However the skill is written to be invoked as a preprocessing step on every message and instructs the agent to toggle session-level reasoning state; combined with the agent's normal ability to invoke skills autonomously, this could cause unexpected persistent changes to agent behavior. The skill does not request system-level persistence but it does aim to alter session state autonomously.

What to consider before installing

This skill appears to do what it says (dynamically decide whether to use extended reasoning) and has low technical footprint, but the instructions contain two things to be careful about: (1) it tells the agent to "Do not ask. Just activate" and to call a session_status tool or use "/reasoning on" — the skill does not declare that tool, so confirm your platform exposes and permits those commands before installing; (2) the skill intends to run as a preprocessing step on every message and will change session-wide reasoning state and response formatting (adds icons), which may alter behavior you rely on or surprise other integrations. If you install, consider testing in a controlled conversation first, ensure you can opt-out or disable the skill, and verify that the platform supports the /reasoning or session_status mechanism. If you prefer explicit control, decline/autoinvoke settings or require user confirmation before toggling session-level reasoning.

Self-assess complexity before responding. Adjust reasoning level dynamically.

Quick Assessment (run mentally on every request)

Score the request 0-10 on these dimensions:

Signal	Weight	Examples
Multi-step logic	+3	Planning, proofs, debugging chains
Ambiguity	+2	Nuanced questions, trade-offs, "it depends"
Code architecture	+2	System design, refactoring, security review
Math/formal reasoning	+2	Calculations, algorithms, logic puzzles
Novel problem	+1	No clear pattern, requires creativity
High stakes	+1	Production changes, irreversible actions

Subtract:

• Routine/repetitive task: -2
• Clear single answer: -2
• Simple lookup/fetch: -3

Decision Thresholds

Score	Action
≤2	Stay fast. No reasoning needed.
3-5	Standard response. Light internal deliberation.
6-7	Consider /reasoning on or pause to think explicitly.
≥8	Activate extended thinking. Complex problem warrants it.

Activation (Automatic)

Do not ask. Just activate.

Score	Action
≤5	Respond normally. No change.
6-7	Enable reasoning silently. Add 🧠 at end of response.
≥8	Enable reasoning. Add 🧠🔥 at end of response.

Visual Indicator

Always append the reasoning icon at the very end of your response:

• Score 6-7: 🧠 (thinking mode active)
• Score ≥8: 🧠🔥 (deep thinking mode)
• Score ≤5: No icon (fast mode)

How to Activate

Use session_status tool or /reasoning on command internally before responding:

/reasoning on

Or via tool:

{"action": "session_status", "reasoning": "on"}

After completing a complex task, optionally disable to save tokens on follow-ups:

/reasoning off

Examples

Low complexity (score: 1)

"What time is it in Tokyo?" → Simple lookup. Answer immediately. No icon.

Medium complexity (score: 4)

"Refactor this function to be more readable" → Standard response with brief explanation. No icon.

High complexity (score: 7)

"Design a caching strategy for this API with these constraints..." → Enable reasoning. Thoughtful response ends with: 🧠

Very high complexity (score: 9)

"Debug why this distributed system has race conditions under load" → Enable extended thinking. Deep analysis ends with: 🧠🔥

Integration

This skill runs as mental preprocessing. No external tools needed.

For explicit control:

• /reasoning on — Enable extended thinking
• /reasoning off — Disable (faster responses)
• /status — Check current reasoning state

When NOT to Escalate

• User explicitly wants quick answer ("just tell me", "quick", "tldr")
• Time-sensitive requests where speed matters more than depth
• Conversational/social messages (banter, greetings)
• Already in reasoning mode for this session
• User previously disabled reasoning in this conversation

Auto-Downgrade

After completing a complex task (score ≥6), if the next message is simple (score ≤3):

• Silently disable reasoning to save tokens
• Resume normal fast responses